Improving Correlation Capture in Generating Imbalanced Data using Differentially Private Conditional GANs
This work addresses the problem of generating synthetic tabular data with privacy guarantees for domains like healthcare, where data imbalance and dependencies are critical, though it appears incremental as it builds on existing GAN and differential privacy methods.
The paper tackles the challenge of generating high-quality, privacy-preserving tabular data for imbalanced datasets by proposing DP-CGANS, a differentially private conditional GAN framework, which outperforms state-of-the-art models in capturing dependencies between variables, as demonstrated on five datasets including real-world health data.
Despite the remarkable success of Generative Adversarial Networks (GANs) on text, images, and videos, generating high-quality tabular data is still under development owing to some unique challenges such as capturing dependencies in imbalanced data, optimizing the quality of synthetic patient data while preserving privacy. In this paper, we propose DP-CGANS, a differentially private conditional GAN framework consisting of data transformation, sampling, conditioning, and networks training to generate realistic and privacy-preserving tabular data. DP-CGANS distinguishes categorical and continuous variables and transforms them to latent space separately. Then, we structure a conditional vector as an additional input to not only presents the minority class in the imbalanced data, but also capture the dependency between variables. We inject statistical noise to the gradients in the networking training process of DP-CGANS to provide a differential privacy guarantee. We extensively evaluate our model with state-of-the-art generative models on three public datasets and two real-world personal health datasets in terms of statistical similarity, machine learning performance, and privacy measurement. We demonstrate that our model outperforms other comparable models, especially in capturing dependency between variables. Finally, we present the balance between data utility and privacy in synthetic data generation considering the different data structure and characteristics of real-world datasets such as imbalance variables, abnormal distributions, and sparsity of data.